Neural networks modelling of streamflow, phosphorus, and suspended solids: application to the Canadian Boreal forest

Abstract

Sediment has long been identified as an important vector for the transport of nutrients and contaminants such as heavy metals and microorganisms. The respective nutrient loading to water bodies can potentially lead to dissolved oxygen depletion, cyanobacteria toxin production and ultimately eutrophication. This study proposed an artificial neural network (ANN) modelling algorithm that relies on low cost readily available meteorological data for simulating streamflow (Q), total suspended solids (TSS) concentration, and total phosphorus (TP) concentration. The models were applied to a 130-km2 watershed in the Canadian Boreal Plain. Our results demonstrated that through careful manipulation of time series analysis and rigorous optimization of ANN configuration, it is possible to simulate Q, TSS, and TP reasonably well. R2 values exceeding 0.89 were obtained for all modelled data cases. The proposed models can provide real time predictions of the modelled parameters, can answer questions related to the impact of climate change scenarios on water quantity and quality, and can be implemented in water resources management through Monte Carlo simulations.